Heart Disease Prediction Using Machine Learning and Deep Learning Techniques

This paper presented an IEEE two-column article on heart disease prediction using machine learning and deep learning techniques. The system uses patient clinical attributes from the StatLog/UCI heart disease dataset and applies preprocessing, feature selection, model training, prediction, visualization, and performance evaluation. The study compares KNN, Naive Bayes, XGBoost, and ANN in Phase II implementation. The experimental results show that ANN achieved the highest performance with 96.2% accuracy, 96.8% precision, 95.9% recall, 96.3% F1-score, and 0.98 ROC-AUC. XGBoost also showed strong performance with 94.8% accuracy and 0.97 ROC-AUC. Compared with Phase I, Phase II improved the best model accuracy from 92.4% to 96.2%. These findings confirm that advanced machine learning and deep learning techniques can improve early heart disease prediction. The proposed system can act as a useful decision-support tool for preliminary screening and risk estimation. It is cost-effective, scalable, and suitable for integration into healthcare applications. However, the system should be considered an assistive tool, and final diagnosis should remain the responsibility of qualified medical professionals. With larger datasets, external validation, explainable AI, and real-time deployment, the system can become more reliable and clinically useful.

[1] C. Ordonez, "Improving heart disease prediction using constrained association rules," Technical Seminar Presentation, University of Tokyo, 2004. [2] F. Le Duff, C. Muntean, M. Cuggia, and P. Mabob, "Predicting survival causes after out of hospital cardiac arrest using data mining method," Studies in Health Technology and Informatics, vol. 107, no. 2, pp. 1256-1259, 2004. [3] W. J. Frawley and G. Piatetsky-Shapiro, "Knowledge discovery in databases: An overview," AI Magazine, vol. 13, no. 3, pp. 57-70, 1996. [4] H. G. Lee, K. Y. Noh, and K. H. Ryu, "Mining bio signal data: Coronary artery disease diagnosis using linear and nonlinear features of HRV," in Proc. International Conference on Emerging Technologies in Knowledge Discovery and Data Mining, 2007, pp. 56-66. [5] K. Noh, H. Lee, H. Shon, B. Lee, and K. Ryu, "Associative classification approach for diagnosing cardiovascular disease," Intelligent Computing in Signal Processing and Pattern Recognition, vol. 345, pp. 721-727, 2006. [6] L. Parthiban and R. Subramanian, "Intelligent heart disease prediction system using CANFIS and genetic algorithm," International Journal of Biological, Biomedical and Medical Sciences, vol. 3, no. 3, pp. 1-8, 2008. [7] N. Guru, A. Dahiya, and N. Rajpal, "Decision support system for heart disease diagnosis using neural network," Delhi Business Review, vol. 8, no. 1, pp. 1-6, 2007. [8] S. Palaniappan and R. Awang, "Intelligent heart disease prediction system using data mining techniques," International Journal of Computer Science and Network Security, vol. 8, no. 8, pp. 1-6, 2008. [9] S. B. Patil and Y. S. Kumaraswamy, "Intelligent and effective heart attack prediction system using data mining and artificial neural network," European Journal of Scientific Research, vol. 31, no. 4, pp. 642-656, 2009. [10] X. Yanwei et al., "Combination data mining models with new medical data to predict outcome of coronary heart disease," in Proc. International Conference on Convergence Information Technology, 2007, pp. 868-872.